Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3928 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.7870. Min Act: 0.0001

Data Index: 1633159 (Python Code)

Max Activating Token Index: 615

Text #1

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.8917. Min Act: 0.0000

Data Index: 1612089 (Python Code)

Max Activating Token Index: 360

Text #2

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.6012. Min Act: -0.0000

Data Index: 1461230 (Python Code)

Max Activating Token Index: 732

Text #3

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.5825. Min Act: -0.0000

Data Index: 1645960 (Python Code)

Max Activating Token Index: 603

Text #4

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.5756. Min Act: -0.0000

Data Index: 1418828 (Python Code)

Max Activating Token Index: 484

Text #5

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.3960. Min Act: -0.0000

Data Index: 1605271 (Python Code)

Max Activating Token Index: 254

Text #6

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.6584. Min Act: -0.0000

Data Index: 1471106 (Python Code)

Max Activating Token Index: 757

Text #7

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.4555. Min Act: -0.0000

Data Index: 1442179 (Python Code)

Max Activating Token Index: 520

Text #8

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.4262. Min Act: -0.0000

Data Index: 1388772 (Python Code)

Max Activating Token Index: 578

Text #9

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.4212. Min Act: 0.0000

Data Index: 1620434 (Python Code)

Max Activating Token Index: 790

Text #10

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.3866. Min Act: 0.0000

Data Index: 1639499 (Python Code)

Max Activating Token Index: 361

Text #11

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.3898. Min Act: -0.0000

Data Index: 1585108 (Python Code)

Max Activating Token Index: 455

Text #12

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.4611. Min Act: -0.0000

Data Index: 1628213 (Python Code)

Max Activating Token Index: 910

Text #13

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.4422. Min Act: -0.0000

Data Index: 1451338 (Python Code)

Max Activating Token Index: 240

Text #14

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.3414. Min Act: -0.0000

Data Index: 1583164 (Python Code)

Max Activating Token Index: 657

Text #15

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.3284. Min Act: -0.0000

Data Index: 1552603 (Python Code)

Max Activating Token Index: 869

Text #16

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.2501. Min Act: -0.0000

Data Index: 1447704 (Python Code)

Max Activating Token Index: 923

Text #17

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.4027. Min Act: -0.0000

Data Index: 1373372 (Python Code)

Max Activating Token Index: 50

Text #18

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.3195. Min Act: -0.0000

Data Index: 1587630 (Python Code)

Max Activating Token Index: 336

Text #19

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.3832. Min Act: 0.0000

Data Index: 1628359 (Python Code)

Max Activating Token Index: 82